An ore sorting method and system under an X-ray image based on a convolutional neural network

Abstract

The invention relates to an ore sorting method and system under an X-ray image based on a convolutional neural network. The method comprises the following steps: artificially selecting different typesof ores as samples and passing the samples through an X-ray machine; dyeing the internal image of the ore according to the original permeability matrix data of the ore; performing classification marking on the dyed image, performing training through a convolutional neural network, and generating a recognition model; and after a to-be-identified ore is dyed through an X-ray machine, predicting thetype and position of the to-be-identified ore. Through the computer artificial intelligence mode, the X-ray machine is used for imaging the interior of the ore; through carrying out deep learning convolutional neural network training on the dyed image imaged by the X-ray machine, the ore content grade can be identified and pre-judged by simulating the mode of evaluating the ore distribution by human experience without other chemical detection means, the accuracy ofmode is close to the accuracy of manual sorting, and real-time, rapid, batched and low-cost sorting can be realized within the tolerance of the sorting industry.

Description

technical field [0001] The invention relates to the field of ore intelligent identification, in particular to a method and system for ore sorting under X-ray images based on a convolutional neural network. Background technique [0002] As the main means of internal detection and analysis of objects, X-ray images were used to detect established objects in the past, such as detecting whether there are dangerous objects such as knives and screwdrivers, or color sorting after dyeing different objects to different colors. To detect a given object, it is necessary to collect images of a large number of objects under X-rays, and perform feature training, and finally be able to detect specific objects within a certain range; the technology of sorting by color is mainly based on the material. Pay attention to the shape of objects, such as detecting all metals, thinking that metals are pending dangerous goods, and then manually checking. [0003] In the field of ore sorting, since th...

AI Technical Summary

Problems solved by technology

[0003] In the field of ore sorting, since the ore and impurities are associated with each other, the ore has no fixed shape and outline, and the material of the ore itself and the impurity have similar transmittance under X-rays, so the separation of ore content can only be done through chemical analysis. However, in the current ore industry, a large number of grades need to be sorted quickly, and the existing technology cannot meet the current needs very well.

Images